#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import cv2
import os
import numpy as np
import sys

# 添加项目根目录到Python路径
current_dir = os.path.dirname(os.path.abspath(__file__))
project_root = os.path.dirname(current_dir)
sys.path.append(project_root)

from utils.detect_dual_track_lines import auto_detect_dual_track_lines

def visualize_dual_track_detection():
    test_dir = 'res/path/dual'
    results = []
    
    # 创建结果保存目录
    result_dir = 'results/dual_track'
    os.makedirs(result_dir, exist_ok=True)
    
    for img_file in sorted(os.listdir(test_dir)):
        if img_file.endswith('.png'):
            img_path = os.path.join(test_dir, img_file)
            print(f'\n处理图片: {img_path}')
            
            # 读取图像
            img = cv2.imread(img_path)
            if img is None:
                print(f'  无法读取图像: {img_path}')
                continue
                
            # 调用自动检测函数，开启观察模式
            result = auto_detect_dual_track_lines(img, observe=True, delay=1000, save_log=True)
            
            # 检查检测结果
            if result[0] is not None:
                center_info, left_info, right_info = result
                
                # 创建结果图像
                result_img = img.copy()
                height, width = img.shape[:2]
                center_x = width // 2
                
                # 绘制左右轨迹线
                left_x1, left_y1, left_x2, left_y2 = left_info["line"]
                right_x1, right_y1, right_x2, right_y2 = right_info["line"]
                
                cv2.line(result_img, (int(left_x1), int(left_y1)), (int(left_x2), int(left_y2)), (255, 0, 0), 2)
                cv2.line(result_img, (int(right_x1), int(right_y1)), (int(right_x2), int(right_y2)), (0, 0, 255), 2)
                
                # 绘制中心线
                center_point = center_info["point"]
                center_line_x1 = (left_x1 + right_x1) // 2
                center_line_y1 = (left_y1 + right_y1) // 2
                cv2.line(result_img, (center_line_x1, center_line_y1), center_point, (0, 255, 0), 2)
                
                # 绘制图像中心线
                cv2.line(result_img, (center_x, 0), (center_x, height), (0, 0, 255), 1)
                
                # 标记中心点
                cv2.circle(result_img, center_point, 10, (255, 0, 255), -1)
                
                # 显示偏差信息
                deviation = center_info["deviation"]
                cv2.putText(result_img, f"偏差: {deviation}px", (10, 30), 
                            cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)
                
                # 显示是否为石板路模式
                stone_path_mode = center_info["stone_path_mode"]
                mode_text = "石板路模式" if stone_path_mode else "标准模式"
                cv2.putText(result_img, mode_text, (10, 60), 
                            cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2)
                
                # 显示检测结果
                cv2.imshow("双轨迹线检测结果", result_img)
                key = cv2.waitKey(0)  # 等待按键
                
                # 保存结果图像
                result_path = os.path.join(result_dir, f"result_{img_file}")
                cv2.imwrite(result_path, result_img)
                print(f'  检测成功! 偏差: {deviation}px, 模式: {mode_text}')
                print(f'  结果已保存至: {result_path}')
                
                # 按ESC键退出
                if key == 27:  # ESC键
                    break
                
                results.append((img_file, True, deviation, stone_path_mode))
            else:
                print(f'  检测失败!')
                results.append((img_file, False, None, None))
    
    # 关闭所有窗口
    cv2.destroyAllWindows()
    
    # 打印检测结果汇总
    print('\n检测结果汇总:')
    success_count = 0
    for img_file, success, deviation, stone_path_mode in results:
        status = '成功' if success else '失败'
        if success:
            success_count += 1
            mode_text = "石板路模式" if stone_path_mode else "标准模式"
            dev_info = f'偏差: {deviation}px, 模式: {mode_text}'
        else:
            dev_info = ''
        print(f'{img_file}: {status} {dev_info}')
    
    success_rate = (success_count / len(results)) * 100 if results else 0
    print(f'\n总成功率: {success_rate:.2f}% ({success_count}/{len(results)})')

if __name__ == "__main__":
    visualize_dual_track_detection()